© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 29854
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stag
    -0.07
    549
    -0.07
    anh
    -0.07
     Zaman
    -0.06
    otron
    -0.06
    egr
    -0.06
     Prem
    -0.06
    teg
    -0.06
    дж
    -0.06
     div
    -0.06
    POSITIVE LOGITS
    LError
    0.07
    eing
    0.07
    XObject
    0.06
    .metamodel
    0.06
    AndGet
    0.06
    amburg
    0.06
     Slut
    0.06
    ALI
    0.06
    ãĤ£
    0.06
    aths
    0.06
    Activations Density 0.000%

    No Known Activations